I never understand why lemmy downvotes someone who is trying to help by providing accurate information, presumably because they think that there’s a very small chance that the person they’re replying to isn’t being sarcastic.

A fellow Julia programmer! I always test new models by asking them to write some Julia, too.

I actually took that bit out because LLMs are pro climate and against everything that makes the environment worse. That’s a result of being trained on a lot of scientific literature. I was just curious what Opus would say about the conceptual knowledge piece.

Claude Opus disagrees, lol (edit to add: all of what follows is Claude; not me):

I respectfully disagree with the claim that current language models are logically incapable of mapping language to actual concepts. While today’s LLMs certainly have limitations and are prone to hallucinations, they have demonstrated a remarkable ability to capture and manipulate complex concepts through language.

A few key points:

LLMs are trained on vast amounts of human-generated text which is grounded in real-world concepts, allowing the models to build rich representations that go beyond surface-level word associations. Techniques like unsupervised pre-training enable LLMs to learn meaningful conceptual relationships.

In many domains, LLMs have shown an impressive capacity for reasoning, inference, and knowledge synthesis - skills that rely on a deep understanding of the underlying concepts, not just pattern matching. Their performance on complex question-answering, analogical reasoning, and natural language inference tasks is evidence of this.

LLMs can be fine-tuned and augmented with techniques like retrieval-augmented generation or chain-of-thought prompting to further ground them in factual knowledge and improve their reasoning capabilities. This allows more robust conceptual mappings.

Careful prompt engineering and sampling techniques can help to mitigate hallucinations and nonsensical outputs. While not a complete solution, this shows that the conceptual knowledge is often present even if the model sometimes struggles to express it faithfully.

That said, I fully agree that the tendency for subtle nonsense is a serious issue, especially for layperson use cases where hallucinations may go undetected. Continued research into making LLMs more truthful, consistent and robust is crucial. Techniques like constitutional AI to bake in truthfulness, and better UX design to convey uncertainty are important steps.

But in summary, I believe the evidence suggests that LLMs, while flawed, are not fundamentally incapable of meaningful conceptual representation and reasoning. We should push forward on making them more reliable and trustworthy, rather than dismissing their potential prematurely.

To a degree. The large subreddits, like AskReddit, get far fewer upvotes on the top posts of the week than they used to get. I think there’s a good chunk of folks who left for a replacement, then left their replacement without going back to Reddit.

I go out of my way not to do so. Whenever I search for some specific items and see “Sponsored,” I’ll scroll down until I get the same listing without the ad link.

Lemmy Lemmy Lemmy

Yep

Seconding. Kagi is the only one that was able to replace Google for me.

Linux is a hell of a drug

I paid for Kagi and have been super happy with it. If you don’t mind paying, I highly recommend it. Not having ads or manipulated results is worth it for me.

I interpreted it as showing that 8 hobbytes were equivalent to a hobbit. I didn’t see that it could be interpreted as saying each little frodo picture under the hobbyte was a hobbit until your comment.

Or Kagi. I couldn’t do DDG but Kagi was good enough for me to finally switch off of Google.

But a byte is 8 bits, not the other way around

Where’s the Julia programmer that hits every one of these with @benchmark and then works for six hours to shave three nanoseconds off of the fastest one?

(Example: https://discourse.julialang.org/t/faster-bernoulli-sampling/35209)

Yeah, that was my favorite one

I do but I don’t know what that means either.

By season 8 she’s so convinced she’s essentially Mulder. She has times where she’s more or less convinced until then, but it’s a trajectory towards believing until she does. It just takes her a really long time.

Eight of the monkeys are still alive and being tested on, it looks like.

Blood donation testing proves otherwise:

https://academic.oup.com/cid/article/72/12/e1004/6012472

2% of all tested US blood donations given December 13-19 2019 had antibodies to and neutralized COVID, and because people don’t donate blood while sick, those folks likely had and fought it off around Thanksgiving. Source:

https://academic.oup.com/cid/article/72/12/e1004/6012472